KR102172361B1 - 불량 검출 장치 및 방법 - Google Patents
불량 검출 장치 및 방법 Download PDFInfo
- Publication number
- KR102172361B1 KR102172361B1 KR1020180152541A KR20180152541A KR102172361B1 KR 102172361 B1 KR102172361 B1 KR 102172361B1 KR 1020180152541 A KR1020180152541 A KR 1020180152541A KR 20180152541 A KR20180152541 A KR 20180152541A KR 102172361 B1 KR102172361 B1 KR 102172361B1
- Authority
- KR
- South Korea
- Prior art keywords
- defect
- location
- unit
- thickness direction
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 222
- 238000000034 method Methods 0.000 title claims description 19
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000012360 testing method Methods 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims description 22
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 11
- 238000005204 segregation Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000000306 recurrent effect Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 230000002950 deficient Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 239000003086 colorant Substances 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 229910001018 Cast iron Inorganic materials 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- CADICXFYUNYKGD-UHFFFAOYSA-N sulfanylidenemanganese Chemical compound [Mn]=S CADICXFYUNYKGD-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Medical Informatics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
Description
도 2는 후판의 탐상 이미지를 얻는 탐상 이미지 장치의 개념도이고,
도 3은 실시예에 따른 후판의 사시도이고,
도 4는 실시예에 따른 판단부의 동작을 설명하는 도면이고,
도 5 내지 도 9는 후판의 불량 종류 별 결함의 위치를 나타낸 이미지이고,
도 10는 본 발명의 실시예에 따른 불량 검출 방법의 흐름도이다.
Claims (6)
- 피검사체의 이미지가 입력되는 입력부;
상기 피검사체의 이미지를 이용하여 피검사체의 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치를 추출하는 제1 추출부; 및
상기 피검사체의 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치를 판별 모델에 입력하여 상기 피검사체의 불량을 판단하는 판단부를 포함하고,
상기 판별 모델은 상기 피검사체의 두께 방향으로 결함 위치에 의해 후보 불량 종류를 출력하고, 길이 방향으로 결함 위치에 의해 최종 불량 종류를 출력하고,
상기 판단부는,
학습 이미지를 획득하는 데이터 획득부; 및
상기 학습 이미지로부터 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치를 추출하는 제2 추출부;를 포함하고,
상기 제2 추출부에서 추출된 상기 두께 방향으로 결함 위치는 피검사체의 두께를 4등분하는 제1 내지 제3 가상선과 결함의 대응 위치로 분리되고,
상기 판단부는 상기 제1 내지 제3 가상선 중 적어도 하나와의 인접 위치에 따라
상기 후보 불량 종류로 편석이나 개재물로 판별하고 상기 판별된 후보 불량 종류와 상기 길이 방향으로 결함 위치를 이용하여 상기 최종 불량 종류를 출력하는 불량 검출 장치.
- 제1항에 있어서,
상기 판단부는,
상기 제2 추출부로부터 추출된 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치에 대하여 기계 학습을 통해 피검사체의 불량 종류를 판단하는 판별 모델을 생성하는 학습부; 및
상기 제1 추출부로부터 추출된 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치를 상기 판별 모델에 입력하여 상기 피검사체의 최종 불량 종류를 판단하는 처리부;를 더 포함하는 불량 검출 장치.
- 삭제
- 제2항에 있어서,
상기 판별 모델은,
상기 제2 추출부로부터 추출된 두께 방향으로 결함 위치 및 길이 방향으로 결함 위치를 입력 데이터로 사용하고, 불량 종류를 출력 데이터로 사용하는 불량 검출 장치.
- 제2항에 있어서,
상기 판별 모델은 CNNs(convolutional neural networks), DNN(Deep Neural Network), RNN(Recurrent Neural Network) 및 BRDNN(Bidirectional Recurrent Deep Neural Network) 중 적어도 하나를 포함하는 불량 검출 장치.
- 제1항에 있어서,
상기 피검사체는 후판이고,
상기 이미지는 탐상 이미지인 불량 검출 장치.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020180152541A KR102172361B1 (ko) | 2018-11-30 | 2018-11-30 | 불량 검출 장치 및 방법 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020180152541A KR102172361B1 (ko) | 2018-11-30 | 2018-11-30 | 불량 검출 장치 및 방법 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20200071819A KR20200071819A (ko) | 2020-06-22 |
KR102172361B1 true KR102172361B1 (ko) | 2020-10-30 |
Family
ID=71142446
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020180152541A Active KR102172361B1 (ko) | 2018-11-30 | 2018-11-30 | 불량 검출 장치 및 방법 |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR102172361B1 (ko) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113466350A (zh) * | 2021-07-23 | 2021-10-01 | 国能新朔铁路有限责任公司 | 故障检测系统及钢轨探伤车 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000146926A (ja) * | 1998-11-13 | 2000-05-26 | Sumitomo Metal Ind Ltd | 欠陥種類弁別方法 |
KR100711494B1 (ko) * | 2005-12-23 | 2007-04-24 | 주식회사 포스코 | 후판의 초음파 탐상 결과 패턴 분류법 |
KR101736613B1 (ko) * | 2015-12-07 | 2017-05-17 | 주식회사 포스코 | 후판 결함 탐상 장치 및 방법 |
JP2018506168A (ja) * | 2014-12-03 | 2018-03-01 | ケーエルエー−テンカー コーポレイション | サンプリング及びフィーチャ選択を伴わない自動欠陥分類 |
-
2018
- 2018-11-30 KR KR1020180152541A patent/KR102172361B1/ko active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000146926A (ja) * | 1998-11-13 | 2000-05-26 | Sumitomo Metal Ind Ltd | 欠陥種類弁別方法 |
KR100711494B1 (ko) * | 2005-12-23 | 2007-04-24 | 주식회사 포스코 | 후판의 초음파 탐상 결과 패턴 분류법 |
JP2018506168A (ja) * | 2014-12-03 | 2018-03-01 | ケーエルエー−テンカー コーポレイション | サンプリング及びフィーチャ選択を伴わない自動欠陥分類 |
KR101736613B1 (ko) * | 2015-12-07 | 2017-05-17 | 주식회사 포스코 | 후판 결함 탐상 장치 및 방법 |
Also Published As
Publication number | Publication date |
---|---|
KR20200071819A (ko) | 2020-06-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230298327A1 (en) | Information processing device, determination method, and information processing program | |
US9297788B2 (en) | Determination assist system of ultrasonic testing, determination assist method of ultrasonic testing, determination assist program of ultrasonic testing, and computer-readable storage medium for storing determination assist program of ultrasonic testing | |
TWI557650B (zh) | 用於識別材料中之缺陷之系統及方法 | |
US10748274B2 (en) | Detecting portions of interest in images | |
CN108876761A (zh) | 图像处理装置、电脑可读取记录媒体、图像处理系统 | |
CN112465027B (zh) | 钢轨伤损检测方法 | |
US20210031507A1 (en) | Identifying differences between images | |
JP6725067B2 (ja) | 不要部分を除去するためのデジタル画像の処理 | |
US20230221286A1 (en) | Inspection device, inspection method, and inspection program | |
US12094098B2 (en) | Defect management apparatus, method and non-transitory computer readable medium | |
CN112308855A (zh) | 钢轨伤损识别模型生成装置、伤损检测装置及系统 | |
CN114266743B (zh) | 基于hsv和cnn的fpc缺陷检测方法、系统及存储介质 | |
KR102172361B1 (ko) | 불량 검출 장치 및 방법 | |
KR101689980B1 (ko) | 패턴 검사 장치 및 패턴 검사 방법 | |
JP4131400B2 (ja) | 鋳造内部欠陥検査支援装置及び方法 | |
Tie et al. | Intelligent detection of dynamic cracking along an interface of brittle material using high-speed photography assisted by data augmentation and machine learning | |
CN113554645B (zh) | 基于wgan的工业异常检测方法和装置 | |
TWI722861B (zh) | 分類方法及分類系統 | |
JP7615067B2 (ja) | 超音波データ評価システム、超音波データ評価方法および判定モデル生成方法 | |
CN114140671B (zh) | 基于多尺度融合的高分辨率芯片图像的分类方法和装置 | |
JP4738243B2 (ja) | 超音波探傷システム | |
JP7215108B2 (ja) | イメージ又はマトリクスデータにおける関心のある部分の検出 | |
US12209992B2 (en) | Method and device for ultrasonic inspection of composite parts, in particular made from carbon fiber reinforced plastics, device and computer program | |
JP7604533B2 (ja) | 欠陥検査装置、欠陥検査方法、教師データ生成方法および判定モデル生成方法 | |
JP7142825B1 (ja) | 画像判定方法及び画像判定システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20181130 |
|
PA0201 | Request for examination | ||
PE0902 | Notice of grounds for rejection |
Comment text: Notification of reason for refusal Patent event date: 20200225 Patent event code: PE09021S01D |
|
PG1501 | Laying open of application | ||
E701 | Decision to grant or registration of patent right | ||
PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 20201023 |
|
GRNT | Written decision to grant | ||
PR0701 | Registration of establishment |
Comment text: Registration of Establishment Patent event date: 20201026 Patent event code: PR07011E01D |
|
PR1002 | Payment of registration fee |
Payment date: 20201027 End annual number: 3 Start annual number: 1 |
|
PG1601 | Publication of registration | ||
PR1001 | Payment of annual fee |
Payment date: 20231019 Start annual number: 4 End annual number: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20241016 Start annual number: 5 End annual number: 5 |